Home > Research > Publications & Outputs > Exact statistical analysis for response-adaptiv...

Research

Associated organisational units

Electronic data

  • 2407.01055v1

    Accepted author manuscript, 925 KB, PDF document

    Available under license: CC BY-NC-SA: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License

Links

Keywords

View graph of relations

Exact statistical analysis for response-adaptive clinical trials: a general and computationally tractable approach

Research output: Working paper › Preprint

Published

Standard

Exact statistical analysis for response-adaptive clinical trials: a general and computationally tractable approach. / Baas, Stef; Jacko, Peter; Villar, Sofía S.
Arxiv, 2024.

Research output: Working paper › Preprint

Harvard

Baas, S, Jacko, P & Villar, SS 2024 'Exact statistical analysis for response-adaptive clinical trials: a general and computationally tractable approach' Arxiv. <https://arxiv.org/abs/2407.01055v1>

APA

Baas, S., Jacko, P., & Villar, S. S. (2024). Exact statistical analysis for response-adaptive clinical trials: a general and computationally tractable approach. Arxiv. https://arxiv.org/abs/2407.01055v1

Vancouver

Baas S, Jacko P, Villar SS. Exact statistical analysis for response-adaptive clinical trials: a general and computationally tractable approach. Arxiv. 2024 Jul 1.

Author

Baas, Stef ; Jacko, Peter ; Villar, Sofía S. / Exact statistical analysis for response-adaptive clinical trials : a general and computationally tractable approach. Arxiv, 2024.

Bibtex

@techreport{37afa5337f964a63a251b3043a183071,
title = "Exact statistical analysis for response-adaptive clinical trials: a general and computationally tractable approach",
abstract = "Response-adaptive (RA) designs of clinical trials allow targeting a given objective by skewing the allocation of participants to treatments based on observed outcomes. RA designs face greater regulatory scrutiny due to potential type I error inflation, which limits their uptake in practice. Existing approaches to type I error control either only work for specific designs, have a risk of Monte Carlo/approximation error, are conservative, or computationally intractable. We develop a general and computationally tractable approach for exact analysis in two-arm RA designs with binary outcomes. We use the approach to construct exact tests applicable to designs that use either randomized or deterministic RA procedures, allowing for complexities such as delayed outcomes, early stopping or allocation of participants in blocks. Our efficient forward recursion implementation allows for testing of two-arm trials with 1,000 participants on a standard computer. Through an illustrative computational study of trials using randomized dynamic programming we show that, contrary to what is known for equal allocation, a conditional exact test has, almost uniformly, higher power than the unconditional test. Two real-world trials with the above-mentioned complexities are re-analyzed to demonstrate the value of our approach in controlling type I error and/or improving the statistical power.",
keywords = "stat.ME",
author = "Stef Baas and Peter Jacko and Villar, {Sof{\'i}a S.}",
note = "35 pages, 6 figures, 11 tables",
year = "2024",
month = jul,
day = "1",
language = "English",
publisher = "Arxiv",
type = "WorkingPaper",
institution = "Arxiv",

}

RIS

TY - UNPB

T1 - Exact statistical analysis for response-adaptive clinical trials

T2 - a general and computationally tractable approach

AU - Baas, Stef

AU - Jacko, Peter

AU - Villar, Sofía S.

N1 - 35 pages, 6 figures, 11 tables

PY - 2024/7/1

Y1 - 2024/7/1

N2 - Response-adaptive (RA) designs of clinical trials allow targeting a given objective by skewing the allocation of participants to treatments based on observed outcomes. RA designs face greater regulatory scrutiny due to potential type I error inflation, which limits their uptake in practice. Existing approaches to type I error control either only work for specific designs, have a risk of Monte Carlo/approximation error, are conservative, or computationally intractable. We develop a general and computationally tractable approach for exact analysis in two-arm RA designs with binary outcomes. We use the approach to construct exact tests applicable to designs that use either randomized or deterministic RA procedures, allowing for complexities such as delayed outcomes, early stopping or allocation of participants in blocks. Our efficient forward recursion implementation allows for testing of two-arm trials with 1,000 participants on a standard computer. Through an illustrative computational study of trials using randomized dynamic programming we show that, contrary to what is known for equal allocation, a conditional exact test has, almost uniformly, higher power than the unconditional test. Two real-world trials with the above-mentioned complexities are re-analyzed to demonstrate the value of our approach in controlling type I error and/or improving the statistical power.

AB - Response-adaptive (RA) designs of clinical trials allow targeting a given objective by skewing the allocation of participants to treatments based on observed outcomes. RA designs face greater regulatory scrutiny due to potential type I error inflation, which limits their uptake in practice. Existing approaches to type I error control either only work for specific designs, have a risk of Monte Carlo/approximation error, are conservative, or computationally intractable. We develop a general and computationally tractable approach for exact analysis in two-arm RA designs with binary outcomes. We use the approach to construct exact tests applicable to designs that use either randomized or deterministic RA procedures, allowing for complexities such as delayed outcomes, early stopping or allocation of participants in blocks. Our efficient forward recursion implementation allows for testing of two-arm trials with 1,000 participants on a standard computer. Through an illustrative computational study of trials using randomized dynamic programming we show that, contrary to what is known for equal allocation, a conditional exact test has, almost uniformly, higher power than the unconditional test. Two real-world trials with the above-mentioned complexities are re-analyzed to demonstrate the value of our approach in controlling type I error and/or improving the statistical power.

KW - stat.ME

M3 - Preprint

BT - Exact statistical analysis for response-adaptive clinical trials

PB - Arxiv

ER -